Teaching
Teaching
Introduction: Introduction to computers and programming paradigms, basic concepts of numbers and number representations.
C programming language elements: Data types, constants, variables, expressions and assignment statements, input and output statements, conditional and branch statements, iteration statements, 1-d and 2-d arrays, functions and parameter passing, recursion, strings, structures, introduction to pointers and dynamic allocation, file read and write.
Searching and sorting: Linear and binary search, selection sort, bubble sort, insertion sort, merge sort, quick sort.
References
Brian W. Kernighan and Dennis M. Ritchie, The C Programming Language, Prentice Hall of India.
E. Balaguruswamy, Programming in ANSI C, Tata McGraw-Hill.
Byron Gottfried, Schaum's Outline of Programming with C, McGraw-Hill.
Seymour Lipschutz, Data Structures, Schaum's Outlines Series, Tata McGraw-Hill.
Course Outline
Digital Image Fundamentals: Imaging and image representation, gray level and histogram, Intensity transformation and image enhancement – contrast intensification, noise cleaning, sharpening, Edge preserving smoothing. Image binarization, segmentation of grey level images, Detection of edges and lines in 2D images, Canny's edge detection algorithm, Hough transform for detecting lines and curves, Colour models, colour representation, colour image processing.
Image Representation and Description Connected-component labelling, connected-component counting, distance transform, medial axis, skeletonization, thinning, Run-length code, Chain code, Polygonal approximation, Boundary descriptors, Moment, Texture (GLCM).
Projective and Camera Geometry: Geometric transformations, projective Geometry, homography properties, Camera geometry, Camera calibration, Stereo vision system, 3D reconstruction, structured light.
Motion analysis and tracking: Motion field, optical flow, motion estimation algorithms – Lucas-Kanade method and Horn-Schunck method, object mean-shift tracking.
Feature Detection and Description: Harris corner detection, histogram of oriented gradients, Scale Invariant Feature Transform (SIFT), Feature description, Matching and model fitting, Dimensionality reduction. Machine Learning in Object Detection: Clustering and Classification, Application of machine learning in object detection and recognition, Application in computer vision problems.
Text / References
• R. C. Gonzalez and R. E. Woods, Digital Image Processing, Pearson.
• Andrew Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press.
• R. Szeleski, Computer Vision: Algorithms & Applications, Springer.
• Forsyth and Ponce, Computer vision: A modern approach, Pearson
• Sonka, Hlavac and Boyle, Image processing, analysis, and Machine vision, Cengage Learning, 2015.